Awesome Ai Agents 2026
Section: Key Papers · Foundation for modern agents (reasoning + acting)
ActiveScore 74
Entry
ReAct
Appears in 7 awesome lists
The foundational paper defining the Thought/Action/Observation loop structure that underlies virtually every agent harness. Required reading for understanding why the loop is structured the way it is and where each harness component maps onto the reasoning-acting cycle.
Found in these lists
Awesome AI Papers
Section: NLP
SlowScore 51
Awesome Artificial Intelligence
Section: Foundational papers · Combined reasoning traces with actions for tool-using language-model agents.
FreshScore 86
Awesome Forward Deployment Engineering (FDE)
Section: The Fundamental Whitepapers · The logic behind how Agentic systems (like Google ADK) actually work.
FreshScore 83
Awesome GPT Prompt Engineering
Section: Papers
SlowScore 65
Awesome Harness Engineering
Section: Agent Loop · The foundational paper defining the Thought/Action/Observation loop structure that underlies virtually every agent harness. Required reading for understanding why the loop is structured the way it is and where each harness component maps onto the reasoning-acting cycle.
FreshScore 88
Awesome Prompts
Section: Foundations · Reasoning + Acting interleaved — foundation of agent prompt design
FreshScore 90
Often listed next to it
ChatGPT
Announcement of ChatGPT, a conversational model trained to answer follow-up questions, admit mistakes, challenge incorrect premises, and reject inappropriate requests. OpenAI blog, November 30, 2022.
In 8 listsDetails
Attention Is All You Need
(AIAYN) - Introducing multi-head self-attention neural networks with positional encoding to do sentence-level NLP without any RNN nor CNN - this paper is a must-read (also see this explanation and this visualization of the paper).
In 6 listsDetails
Training language models to follow instructions with human feedback
This paper presents an RLHF approach to using supervised learning to fine-tuning. It is also known as a paper that illustrates the kernel of ChatGPT's thinking. Presumably, ChatGPT is an extended version of InstructGPT that enables fine-tuning on larger datasets.
In 6 listsDetails
Chain-of-Thought Prompting
foundational result; intermediate reasoning steps improve performance.
In 5 listsDetails
HuggingGPT
Solving AI Tasks with ChatGPT and its Friends in HuggingFace
In 5 listsDetails
Generative Agents: Interactive Simulacra of Human Behavior
a paper that presents computational software agents that simulate believable human behavior
In 5 listsDetails
Tree of Thoughts
search over reasoning trees.
In 4 listsDetails
Language Models are Few-Shot Learners
by Tom B. Brown (OpenAI) et al. - "We train GPT-3, an autoregressive language model with 175 billion parameters :scream:, 10x more than any previous non-sparse language model, and test its performance in the few-shot setting."
In 4 lists